Outmake Models
Models

Yi 1.5 6B

01-ai · May 2024

Get Hugging Face

A 6.1B chat model from 01-ai.

Downloads
37K
Likes
11
Parameters
6.1B
Context
4K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q8_0 size from bartowski is the one to get: a 6.4 GB download that uses 6.7 GB of memory, and writes about 8.9 words a second.

Ratings

KnowledgeMMLU-Pro
38.2%

MMLU-Pro: graduate-level questions in 14 subjects. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.

Yi 1.5 6B runs well from a Mac with an M1 and 8 GB of memory. 59 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From bartowski/Yi-1.5-6B-Chat-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ1_S1.4 GB1.9 GBestimatedOpen
IQ1_M1.5 GB2.0 GBestimatedOpen
IQ2_XXS1.7 GB2.1 GBestimatedOpen
IQ2_XS1.9 GB2.3 GBestimatedOpen
IQ2_S2.0 GB2.4 GBestimatedOpen
IQ2_M2.2 GB2.6 GBestimatedOpen
IQ3_XXS2.4 GB2.8 GBestimatedOpen
IQ3_XS2.6 GB3.0 GBestimatedOpen
IQ3_S2.7 GB3.1 GBestimatedOpen
IQ3_M2.8 GB3.2 GBestimatedOpen
IQ4_XS3.3 GB3.7 GBestimatedOpen
IQ4_NL3.5 GB3.9 GBestimatedOpen
Q8_06.4 GB6.9 GBestimatedOpen
F3224 GB25 GBestimatedOpen

Run It Anywhere

Yi 1.5 6B is an open model, so any app that runs GGUF files can run it. These take the Q8_0 size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/Yi-1.5-6B-Chat-GGUF:Q8_0
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/Yi-1.5-6B-Chat-GGUF:Q8_0
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/Yi-1.5-6B-Chat-GGUF:Q8_0
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBIQ4_NL3.5 GB3.9 GB
8 GBQ8_06.4 GB6.9 GB
10 GBQ8_06.4 GB6.9 GB
11 GBQ8_06.4 GB6.9 GB
12 GBQ8_06.4 GB6.9 GB
16 GBQ8_06.4 GB6.9 GB
20 GBQ8_06.4 GB6.9 GB
24 GBQ8_06.4 GB6.9 GB
32 GBF3224 GB25 GB
48 GBF3224 GB25 GB

The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.

On every Mac
MacSizeFitMemoryWrites
M6 · 16 GBQ8_0Runs great6.7 GB13
M6 · 24 GBQ8_0Runs great6.7 GB13
M6 · 32 GBQ8_0Runs great6.7 GB13
M5 · 16 GBQ8_0Runs great6.7 GB12
M5 · 24 GBQ8_0Runs great6.7 GB12
M5 · 32 GBQ8_0Runs great6.7 GB12
M5 Pro · 24 GBQ8_0Runs great6.7 GB23
M5 Pro · 48 GBQ8_0Runs great6.7 GB23
M5 Pro · 64 GBQ8_0Runs great6.7 GB23
M5 Max · 36 GBQ8_0Runs great6.7 GB35
M5 Max · 48 GBQ8_0Runs great6.7 GB45
M5 Max · 64 GBQ8_0Runs great6.7 GB45
M5 Max · 128 GBQ8_0Runs great6.7 GB45
M5 Ultra · 96 GBQ8_0Runs great6.7 GB84
M5 Ultra · 256 GBQ8_0Runs great6.7 GB84
M5 Ultra · 512 GBQ8_0Runs great6.7 GB84
M4 · 16 GBQ8_0Runs great6.7 GB8.9
M4 · 24 GBQ8_0Runs great6.7 GB8.9
M4 · 32 GBQ8_0Runs great6.7 GB8.9
M4 Pro · 24 GBQ8_0Runs great6.7 GB19
M4 Pro · 48 GBQ8_0Runs great6.7 GB19
M4 Pro · 64 GBQ8_0Runs great6.7 GB19
M4 Max · 36 GBQ8_0Runs great6.7 GB27
M4 Max · 48 GBQ8_0Runs great6.7 GB34
M4 Max · 64 GBQ8_0Runs great6.7 GB34
M4 Max · 96 GBQ8_0Runs great6.7 GB27
M4 Max · 128 GBQ8_0Runs great6.7 GB34
M3 · 8 GBQ4_K_SRuns great3.8 GB9.9
M3 · 16 GBQ8_0Runs great6.7 GB7.6
M3 · 24 GBQ8_0Runs great6.7 GB7.6
M3 Pro · 18 GBQ8_0Runs great6.7 GB11
M3 Pro · 36 GBQ8_0Runs great6.7 GB11
M3 Max · 36 GBQ8_0Runs great6.7 GB21
M3 Max · 48 GBQ8_0Runs great6.7 GB27
M3 Max · 64 GBQ8_0Runs great6.7 GB27
M3 Max · 96 GBQ8_0Runs great6.7 GB21
M3 Max · 128 GBQ8_0Runs great6.7 GB27
M3 Ultra · 96 GBQ8_0Runs great6.7 GB47
M3 Ultra · 256 GBQ8_0Runs great6.7 GB47
M3 Ultra · 512 GBQ8_0Runs great6.7 GB47
M2 · 8 GBQ4_K_SRuns great3.8 GB9.9
M2 · 16 GBQ8_0Runs great6.7 GB7.6
M2 · 24 GBQ8_0Runs great6.7 GB7.6
M2 Pro · 16 GBQ8_0Runs great6.7 GB15
M2 Pro · 32 GBQ8_0Runs great6.7 GB15
M2 Max · 32 GBQ8_0Runs great6.7 GB27
M2 Max · 64 GBQ8_0Runs great6.7 GB27
M2 Max · 96 GBQ8_0Runs great6.7 GB27
M2 Ultra · 64 GBQ8_0Runs great6.7 GB46
M2 Ultra · 128 GBQ8_0Runs great6.7 GB46
M2 Ultra · 192 GBQ8_0Runs great6.7 GB46
M1 · 8 GBQ4_K_SRuns great3.8 GB6.7
M1 · 16 GBQ8_0Runs great6.7 GB5.1
M1 Pro · 16 GBQ8_0Runs great6.7 GB14
M1 Pro · 32 GBQ8_0Runs great6.7 GB14
M1 Max · 32 GBQ8_0Runs great6.7 GB24
M1 Max · 64 GBQ8_0Runs great6.7 GB24
M1 Ultra · 64 GBQ8_0Runs great6.7 GB40
M1 Ultra · 128 GBQ8_0Runs great6.7 GB40

Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.

Packaged by

2 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.

Information

Maker
01-ai
Released
May 2024
Parameters
6.1B
Longest chat
4K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
36,866
Likes
11
Sizes
14, 1.4 to 24 GB
Kind
Maker's release

Badge for the model card

Shows on Yi 1.5 6B's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

Runs on Mac badge

Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.

Your Computer

Every model is judged for this Mac. Both are under About This Mac, in the Apple menu.

Every Mac · Every graphics card

Civitai

Open in OutmakeHugging Face

New to Outmake? Download the free beta